Ogen

Bind a live source

bind_source

Bind a key to a live, read-only source: a JSON endpoint, a Postgres/Supabase table, an Airtable table, a Google Sheet, a HubSpot object, a tool on another MCP server, a Salesforce SOQL query, a NetSuite SuiteQL query, a one-row SELECT against a raw Postgres database, or a Priority ERP OData read. Every recall reads it fresh — nothing here is cached as truth. Record only.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	Yes	The key to bind.
`url`	No	For a plain JSON endpoint: an https:// URL, the live source for this key. Omit when using `source` instead.
`field`	No	For a plain JSON endpoint only: an optional dotted path to one value in the response, e.g. "status" or "data.items.0.total" (object keys or array indexes, up to 16 segments). Recall then answers with just that value. A missing path, a body that isn't JSON, or a null there comes back unavailable with reason field_missing, not_json or field_null, and a detail naming the missing segment. Omit it to get the whole body.
`source`	No	Instead of a plain endpoint: a Postgres/Supabase table (postgrest), an Airtable table, a Google Sheet, a HubSpot object, a tool on another MCP server (mcp), a Salesforce SOQL query (salesforce), a NetSuite SuiteQL query (netsuite), a one-row SELECT against a raw Postgres database (postgres) — direct SQL, read-only — or a Priority ERP OData read (priority): base_url, username/password (or Priority's own application credentials, sent the same way), form, filter, field. Fields depend on kind. For salesforce/netsuite/hubspot/airtable/postgrest/postgres/priority, pass connection: "<name>" (see connections action "set") instead of that kind's own credential fields.
`headers`	No	For a plain JSON endpoint only: optional request headers (e.g. an auth token), up to 16. Stored encrypted at rest.
`alongside`	No	Bind a SECOND (or third, or fourth) live source to this key instead of replacing the one it already has. When the bound systems disagree, the act holds and whoever decides sees every reading, labelled by system. Omit this (the default) to replace the key's one source, removing any other source already bound alongside it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 30, 2026

addedInput schema / properties / alongside

Added value: +{
+  "description": "Bind a SECOND (or third, or fourth) live source to this key instead of replacing the one it already has. When the bound systems disagree, the act holds and whoever decides sees every reading, labelled by system. Omit this (the default) to replace the key's one source, removing any other source already bound alongside it.",
+  "type": "boolean"
+}

Changed1 schema field changedSep 26, 2026

changedInput schema / properties / headers / description

Previous value: -"For a plain JSON endpoint only: optional request headers (e.g. an auth token). Stored encrypted at rest."New value: +"For a plain JSON endpoint only: optional request headers (e.g. an auth token), up to 16. Stored encrypted at rest."

Changed1 schema field changedSep 26, 2026

changedInput schema / properties / source / description

Previous value: -"Instead of a plain endpoint: a Postgres/Supabase table (postgrest), an Airtable table, a Google Sheet, a HubSpot object, a tool on another MCP server (mcp), a Salesforce SOQL query (salesforce), a NetSuite SuiteQL query (netsuite), a one-row SELECT against a raw Postgres database (postgres) — direct SQL, read-only — or a Priority ERP OData read (priority): base_url, username/password (or Priority's own application credentials, sent the same way), form, filter, field. Fields depend on kind. For salesforce/netsuite/hubspot/airtable/postgrest/postgres/priority, pass connection: \"<name>\" (see set_connection) instead of that kind's own credential fields."New value: +"Instead of a plain endpoint: a Postgres/Supabase table (postgrest), an Airtable table, a Google Sheet, a HubSpot object, a tool on another MCP server (mcp), a Salesforce SOQL query (salesforce), a NetSuite SuiteQL query (netsuite), a one-row SELECT against a raw Postgres database (postgres) — direct SQL, read-only — or a Priority ERP OData read (priority): base_url, username/password (or Priority's own application credentials, sent the same way), form, filter, field. Fields depend on kind. For salesforce/netsuite/hubspot/airtable/postgrest/postgres/priority, pass connection: \"<name>\" (see connections action \"set\") instead of that kind's own credential fields."

Changed1 schema field changedSep 25, 2026

addedInput schema / properties / field

Added value: +{
+  "description": "For a plain JSON endpoint only: an optional dotted path to one value in the response, e.g. \"status\" or \"data.items.0.total\" (object keys or array indexes, up to 16 segments). Recall then answers with just that value. A missing path, a body that isn't JSON, or a null there comes back unavailable with reason field_missing, not_json or field_null, and a detail naming the missing segment. Omit it to get the whole body.",
+  "type": "string"
+}

First observedSep 24, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, and it does disclose meaningful traits: the source is read-only, 'Every recall reads it fresh — nothing here is cached as truth' (freshness semantics), and 'Record only' (this registers a binding, it does not fetch). It stops short of stating auth/permission requirements or what happens when binding to an already-bound key, though the schema covers replacement and encryption-at-rest.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Compact and front-loaded: the core action and its read-only, fresh-read nature lead, with the source enumeration following. The long comma-separated kind list is somewhat redundant with the schema enum but is defensible as a scannable summary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a no-output-schema configuration tool, the description plus the unusually detailed schema together cover the essentials — what binding does, source kinds, and the alongside/replace behavior. It could say more about what a successful bind returns or key-collision handling, but nothing critical is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents key, url, field, source, headers, and alongside in rich detail. The description mostly restates the source-kind list that the schema's `kind` enum already carries, adding little parameter meaning beyond what is structured.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (bind) and resource (a key to a live, read-only source) and enumerates the full set of supported source kinds, so an agent knows exactly what operation is performed. It does not, however, name or contrast itself against the obvious sibling recall_live_fact, leaving the read/write-config distinction to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'Record only' and 'read-only source' suggest this configures a binding rather than reading data, which nudges the agent away from recall_live_fact. There is no explicit when-to-use statement, no mention of prerequisites, and no routing guidance to alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Ogen tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?